The Agent Skills Directory

[SAFE]: The skill facilitates standard engineering workflows, specifically automated unit testing and refactoring, within the LedgerHQ development environment.
[COMMAND_EXECUTION]: The skill executes local shell commands using pnpm to measure coverage and execute tests. This behavior is expected and appropriate for its stated purpose of improving test coverage.
Evidence: pnpm <mobile|desktop> test:jest --coverage ... in SKILL.md.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests content from external Jira tickets, which is common for this type of agent skill.
Ingestion points: Jira ticket URLs ($TARGET_ZONE) processed via Atlassian MCP in SKILL.md.
Boundary markers: None explicitly defined for the external data ingestion.
Capability inventory: File system modification (writing and refactoring test files), shell command execution (pnpm).
Sanitization: No explicit sanitization or validation of ticket content is mentioned.

test-coverage